Pınar CİHAN, Erhan GÖKÇE, Ali Haydar KIRMIZIGÜL, Onur ATAKİŞİ, Hidayet Metin ERDOĞAN

Yapay Zeka Yöntemleri İle Kuzularda İmmünoglobulin G Tahmini

Yenidoğan ruminantların sağlığı, ölüm ve hastalık oranları, kolostrum kalitesine ve emilen Immunoglobulin G (IgG) miktarına bağlıdır. Konvansiyonel yöntemlerle IgG konsantrasyonunun ölçülmesi maliyetli olduğundan, bilgisayar destekli tahminler önemlidir. Bu çalışmada, gama-glutamil transferaz (GGT) enzim aktivitesi, toplam protein (TP) ve albümin (ALB) değerlerinden serum IgG konsantrasyonunu tahmin etmek için yapay sinir ağı (YSA), çok değişkenli uyarlanabilir regresyon eğrileri (MARS), destek vektör regresyonu (SVR) ve bulanık sinir ağı (FNN) modelleri kullanılmıştır. Parametreler arasındaki korelasyon incelenmiş ve serum IgG konsantrasyonunun, GGT ve TP ile pozitif, ALB ile negatif korelasyonlu olduğu görülmüştür (sırasıyla R = 0.75, P

Prediction of Immunoglobulin G in Lambs with Artificial Intelligence Methods

The health, mortality and morbidity rates of neonatal ruminants depend on colostrum quality and the amount of Immunoglobulin G (IgG) absorbed. Computer-aided estimates are important as measuring IgG concentration with conventional methods is costly. In this study, artificial neural network (ANN), multivariate adaptive regression splines (MARS), support vector regression (SVR) and fuzzy neural network (FNN) models were used to predict the serum IgG concentration from gamma-glutamyl transferase (GGT) enzyme activity, total protein (TP) concentration and albumin (ALB). The correlation between parameters was examined. IgG positively correlated with GGT and TP and negatively correlated with ALB (R = 0.75, P

PDF

___

1. Gokce E, Atakisi O, Kirmizigul AH, Unver A, Erdogan HM: Passive immunity in lambs: Serum lactoferrin concentrations as a predictor of IgG concentration and its relation to health status from birth to 12 weeks of life. Small Ruminant Res, 116 (2-3): 219-228, 2014. DOI: 10.1016/j. smallrumres.2013.11.006
2. Weaver DM, Tyler JW, VanMetre DC, Hostetler DE, Barrington GM: Passive transfer of colostral immunoglobulins in calves. J Vet Intern Med, 14 (6): 569-577, 2000. DOI: 10.1892/0891-6640(2000)014<0569:pt ocii>2.3.co;2
3. Bekele T, Kasali OB, Woldeab T: Causes of lamb morbidity and mortality in the Ethiopian highlands. Vet Res Commun, 16 (6): 415-424, 1992. DOI: 10.1007/BF01839018
4. Gilbert RP, Gaskins CT, Hillers JK, Parker CF, McGuire TC: Genetic and environmental factors affecting immunoglobulin G1 concentrations in ewe colostrum and lamb serum. J Anim Sci, 66 (4): 855-863, 1988. DOI: 10.2527/jas1988.664855x
5. Gokce E, Erdogan HM: An epidemiological study on neonatal lamb health. Kafkas Univ Vet Fak Derg, 15 (2): 225-236, 2009. DOI: 10.9775/ kvfd.2008.104-A
6. Gökçe E, Kırmızıgül AH, Erdoğan HM, Çitil M: Risk factors associated with passive immunity, health, birth weight and growth performance in lambs: I. Effect of parity, dam’s health, birth weight, gender, type of birth and lambing season on morbidity and mortality. Kafkas Univ Vet Fak Derg, 19 (Suppl-A): A153-A160, 2013. DOI: 10.9775/kvfd.2012.8440
7. Stelwagen K, Carpenter E, Haigh B, Hodgkinson A, Wheeler TT: Immune components of bovine colostrum and milk. J Anim Sci, 87 (Suppl-13): 3-9, 2009. DOI: 10.2527/jas.2008-1377
8. Gökçe E, Kırmızıgül AH, Atakişi O, Erdoğan HM: Risk factors associated with passive immunity, health, birth weight and growth performance in lambs: III. The relationship among passive immunity, birth weight gender, birth type, parity, dam’s health and lambing season. Kafkas Univ Vet Fak Derg, 19 (5): 741-747, 2013. DOI: 10.9775/kvfd.2013.8441
9. Waldner CL, Rosengren LB: Factors associated with serum immunoglobulin levels in beef calves from Alberta and Saskatchewan and association between passive transfer and health outcomes. Can Vet J, 50 (3): 275-281, 2009.
10. Castro N, Capote J, Bruckmaier RM, Argüello A: Management effects on colostrogenesis in small ruminants: A review. J Appl Anim Res, 39 (2): 85-93, 2011. DOI: 10.1080/09712119.2011.581625
11. Fahey JL, McKelvey EM: Quantitative determination of serum immunoglobulins in antibody-agar plates. J Immunol, 94 (1): 84-90, 1965.
12. Lee SH, Jaekal J, Bae CS, Chung BH, Yun SC, Gwak MJ, Noh GJ, Lee DH: Enzyme‐linked ımmunosorbent assay, single radial ımmunodiffusion, and ındirect methods for the detection of failure of transfer of passive ımmunity in dairy calves. J Vet Intern Med, 22 (1): 212-218, 2008. DOI: 10.1111/j.1939-1676.2007.0013.x
13. Zarrilli A, Micera E, Lacarpia N, Lombardi P, Pero ME, Pelagalli A, d’Angelo D, Mattia M, Avallone L: Evaluation of ewe colostrum quality by estimation of enzyme activity levels. Revue Méd Vét, 154 (8-9): 521-523, 2003.
14. Brownlee J: Master Machine Learning Algorithms: Discover how They Work and implement Them from Scratch. Machine Learning Mastery, 2016.
15. Gupta M, Konar D, Bhattacharyya S, Biswas S: Computer Vision and Machine Intelligence in Medical Image Analysis. Springer, 2020.
16. Chopra P, Sharma RK, Kumar M, Chopra T: Comparison of machine learning techniques for the prediction of compressive strength of concrete. Adv Civil Eng, 2018:5481705, 2018. DOI: 10.1155/2018/5481705
17. Cihan MT: Prediction of Concrete Compressive Strength and Slump by Machine Learning Methods. Adv Civil Eng, 2019:3069046, 2019. DOI: 10.1155/2019/3069046
18. Gevrekci Y, Altıntaş V, Yeğenoğlu ED, Takma Ç, Atıl H, Sesli M: A fuzzy logic application to predict egg production on laying hens. Kafkas Univ Vet Fak Derg, 25 (1): 111-118, 2019. DOI: 10.9775/kvfd.2018.20447
19. Cihan P, Gökçe E, Kalıpsız O: A review of machine learning applications in veterinary field. Kafkas Univ Vet Fak Derg, 23 (4): 673-680, 2017. DOI: 10.9775/kvfd.2016.17281
20. Cihan P, Kalıpsız O, Gökçe E: Hayvan hastalığı teşhisinde normalizasyon tekniklerinin yapay sinir ağı ve özellik seçim performansına etkisi. Turkish Studies, 12 (11), 59-70, 2017. DOI: 10.7827/TurkishStudies.11902
21. Haykin S: Neural Networks: A comprehensive Foundation. Prentice- Hall, Inc., 2007.
22. Friedman JH: Multivariate adaptive regression splines. Ann Stat, 19 (1): 1-67, 1991.
23. Vapnik V: The nature of statistical learning theory. Springer science & business media, 2013.
24. Buckley JJ, Hayashi Y: Fuzzy neural networks: A survey. Fuzzy Sets Syst, 66 (1): 1-13, 1994.
25. Zadeh LA: Fuzzy sets. Fuzzy sets, fuzzy logic, and fuzzy systems: Selected papers by Lotfi A Zadehed., 394-432, World Scientific, 1996.
26. Yager RR, Filev DP: Essentials of fuzzy modeling and control. John Wiley, New York, 1994.
27. Adebayo AD, Adekoya AF, Rahman MT: Predicting stock trends using Tsk-fuzzy rule based system. JENRM, 4 (7): 48-55, 2017.
28. Alcalá R, Cordón O, Casillas J, Herrera F, Zwir S: Learning and tuning fuzzy rule-based systems for linguistic modeling. Knowledge-Based Systemsed., 889-941, Elsevier, 2000.
29. Cavallaro F: A Takagi-Sugeno fuzzy inference system for developing a sustainability index of biomass. Sustainability, 7 (9): 12359-12371, 2015.
30. Massimini G, Britti D, Peli A, Cinotti S: Effect of passive transfer status on preweaning growth performance in dairy lambs. J Am Vet Med Assoc, 229 (1): 111-115, 2006.
31. Vihan VS: Immunoglobulin levels and their effect on neonatal survival in sheep and goats. Small Ruminant Res, 1 (2): 135-144, 1988. DOI: 10.1016/0921-4488(88)90029-6
32. Andrés S, Jiménez A, Sánchez J, Alonso JM, Gómez L, Lopez F, Rey J: Evaluation of some etiological factors predisposing to diarrhoea in lambs in “La Serena”(Southwest Spain). Small Ruminant Res, 70 (2-3): 272- 275, 2007. DOI: 10.1016/j.smallrumres.2006.04.004
33. Brujeni GN, Jani SS, Alidadi N, Tabatabaei S, Sharifi H, Mohri M: Passive immune transfer in fat-tailed sheep: Evaluation with different methods. Small Ruminant Res, 90 (1-3): 146-149, 2010. DOI: 10.1016/j. smallrumres.2009.12.024
34. Gökçe E, Atakişi O, Kırmızıgül AH, Erdoğan HM: Risk factors associated with passive immunity, health, birth weight and growth performance in lambs: II. Effects of passive immunity and some risk factors on growth performance during the first 12 weeks of life. Kafkas Univ Vet Fak Derg, 19 (4): 619-627, 2013. DOI: 10.9775/kvfd.2013.8442
35. Gökçe E, Atakisi O, Kırmızıgül AH, Erdoğan HM: Interrelationships of serum and colostral ıgg (passive ımmunity) with total protein concentrations and health status in lambs. Kafkas Univ Vet Fak Derg, 25 (4): 587, 2019. DOI: 10.9775/kvfd.2018.21035/Err
36. Sawyer M, Willadsen C, Osburn BI, McGuire TC: Passive transfer of colostral immunoglobulins from ewe to lamb and its influence on neonatal lamb mortality. J Am Vet Med Assoc, 171 (12): 1255-1259, 1977.
37. Hunter AG, Reneau JK, Williams JB: Factors affecting IgG concentration in day-old lambs. J Anim Sci, 45 (5): 1146-1151, 1977. DOI: 10.2527/ jas1977.4551146x
38. Pekcan M, Fidanci UR, Yuceer B, Ozbeyaz C: Estimation of passive immunity in newborn calves with routine clinical chemistry measurements. Ankara Üniv Vet Fak Derg, 60 (2): 85-88, 2013.
39. Britti D, Massimini G, Peli A, Luciani A, Boari A: Evaluation of serum enzyme activities as predictors of passive transfer status in lambs. J Am Vet Med Assoc, 226 (6): 951-955, 2005. DOI: 10.2460/javma.2005.226.951
40. Maden M, Altunok V, Birdane FM, Aslan V, Nizamlioglu M: Blood and colostrum/milk serum γ‐glutamyltransferase activity as a predictor of passive transfer status in lambs. J Vet Med Series B, 50 (3): 128-131, 2003. DOI: 10.1046/j.1439-0450.2003.00629.x
41. Mee JF, O’farrell KJ, Reitsma P, Mehra R: Effect of a whey protein concentrate used as a colostrum substitute or supplement on calf immunity, weight gain, and health. J Dairy Sci, 79 (5): 886-894, 1996. DOI: 10.3168/jds.S0022-0302(96)76437-8
42. Quigley III JD, Kost CJ, Wolfe TM: Absorption of protein and IgG in calves fed a colostrum supplement or replacer. J Dairy Sci, 85 (5): 1243- 1248, 2002. DOI: 10.3168/jds.S0022-0302(02)74188-X